OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers Paper • 2607.04033 • Published 4 days ago • 68
FWE - Transformer++ 340M Collection OpenTome optimizer benchmark — FWE - Transformer++ 340M • 12 items • Updated 23 days ago • 2
FWE - Transformer++ 1B Collection OpenTome optimizer benchmark — FWE - Transformer++ 1B • 12 items • Updated 23 days ago